Estimation of total body fat using symbolic regression and evolutionary algorithms
Jose-Manuel Muñoz, Odin Morón-García, J. Ignacio Hidalgo, Omar Costilla-Reyes
TL;DR
The paper addresses estimating total body fat percentage (BFP) using interpretable symbolic models derived from grammar-guided genetic programming. It compares Grammatical Evolution (GE), Context-Free Grammar Genetic Programming (CFG-GP), and Dynamic Structured Grammatical Evolution (DSGE) on NHANES 2017-18 data, benchmarking against the QLattice SR framework. The study finds that DSGE provides the most stable and accurate results (\(R^2 \approx 0.85\), RMSE around \(3.4\)), with CFG-GP offering competitive yet more variable performance and GE lagging. The work demonstrates that interpretable, grammar-guided symbolic expressions can match prior SR approaches in accuracy while delivering transparent, clinically usable formulas for BFP estimation, aiding metabolic health assessment.
Abstract
Body fat percentage is an increasingly popular alternative to Body Mass Index to measure overweight and obesity, offering a more accurate representation of body composition. In this work, we evaluate three evolutionary computation techniques, Grammatical Evolution, Context-Free Grammar Genetic Programming, and Dynamic Structured Grammatical Evolution, to derive an interpretable mathematical expression to estimate the percentage of body fat that are also accurate. Our primary objective is to obtain a model that balances accuracy with explainability, making it useful for clinical and health applications. We compare the performance of the three variants on a public anthropometric dataset and compare the results obtained with the QLattice framework. Experimental results show that grammatical evolution techniques can obtain competitive results in performance and interpretability.